{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:42:17Z","timestamp":1785858137793,"version":"3.56.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,18]]},"DOI":"10.1109\/itsc60802.2025.11423568","type":"proceedings-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:10:23Z","timestamp":1773691823000},"page":"1020-1027","source":"Crossref","is-referenced-by-count":3,"title":["Towards Human-Centric Autonomous Driving: A Fast-Slow Architecture Integrating Large Language Model Guidance with Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Chengkai","family":"Xu","sequence":"first","affiliation":[{"name":"College of Transportation, Tongji University,Shanghai,China,201804"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Transportation, Tongji University,Shanghai,China,201804"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yicheng","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Transportation, Tongji University,Shanghai,China,201804"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Transportation, Tongji University,Shanghai,China,201804"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Hang","sequence":"additional","affiliation":[{"name":"College of Transportation, Tongji University,Shanghai,China,201804"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Transportation, Tongji University,Shanghai,China,201804"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3223131"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3402136"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2022.3144956"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3474469"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104654"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref9","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Dilu: A knowledgedriven approach to autonomous driving with large language models","author":"Wen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Languagempc: Large language models as decision makers for autonomous driving","author":"Sha","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Thinking, fast and slow","author":"Kahneman","year":"2011","journal-title":"macmillan"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3380074"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3551098"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2023.128517"},{"key":"ref17","article-title":"A survey of reinforcement learning from human feedback","volume":"10","author":"Kaufmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.05.017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3384992"},{"key":"ref20","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"International conference on machine learning","author":"Cobbe","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/wacvw60836.2024.00108"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3528051"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref25","article-title":"Tell-drive: Enhancing autonomous driving with teacher 11 m-guided deep reinforcement learning","author":"Xu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Llm4drive: A survey of large language models for autonomous driving","volume-title":"NeurIPS 2024 Workshop on Open-World Agents","author":"Yang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.09.007"},{"key":"ref30","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3918"},{"key":"ref32","article-title":"Interact, instruct to improve: A 11 m-driven parallel actor-reasoner framework for enhancing autonomous vehicle interactions","author":"Fang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","volume-title":"An environment for autonomous driving decisionmaking","author":"Leurent","year":"2018"},{"key":"ref37","article-title":"Gymnasium: A standard interface for reinforcement learning environments","author":"Towers","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","location":"Gold Coast, Australia","start":{"date-parts":[[2025,11,18]]},"end":{"date-parts":[[2025,11,21]]}},"container-title":["2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11422813\/11423000\/11423568.pdf?arnumber=11423568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:49:15Z","timestamp":1773726555000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11423568\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/itsc60802.2025.11423568","relation":{},"subject":[],"published":{"date-parts":[[2025,11,18]]}}}